© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57443
    Prev
    Next
    INDEX
    Explanations

    Nobel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第ä¸ī次
    -0.30
    inee
    -0.27
    ä»ĥ
    -0.27
    æĿĢèıĮ
    -0.26
    itten
    -0.25
     dyn
    -0.25
    /***/
    -0.24
    Danger
    -0.24
    Calling
    -0.24
    orary
    -0.24
    POSITIVE LOGITS
    uchs
    0.27
    ButtonItem
    0.27
    示
    0.25
    äºīè®®
    0.25
    (dispatch
    0.25
    ì§ĢìĽIJ
    0.25
    asters
    0.24
    Hook
    0.24
    paration
    0.24
    ock
    0.23
    Activations Density 0.001%

    No Known Activations